Training in progress, epoch 0

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

adapter_config.json

@@ -0,0 +1,36 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Phi-4-mini-instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "gate_up_proj",
+    "qkv_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0756b9807db55b87b717f807efd250d1c7cc702cb1baa5e0ac889821ec0fbfa
+size 46171456

added_tokens.json

@@ -0,0 +1,13 @@
+{
+  "<|/tool_call|>": 200026,
+  "<|/tool|>": 200024,
+  "<|assistant|>": 200019,
+  "<|end|>": 200020,
+  "<|im_end|>": 200029,
+  "<|system|>": 200022,
+  "<|tag|>": 200028,
+  "<|tool_call|>": 200025,
+  "<|tool_response|>": 200027,
+  "<|tool|>": 200023,
+  "<|user|>": 200021
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8799b7ce62bf40e724f80af87b9545f9d9043778f435040a6c08e834dc047b69
+size 15524282

tokenizer_config.json

@@ -0,0 +1,122 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "199999": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200018": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200019": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200020": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200021": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200022": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200023": {
+      "content": "<|tool|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200024": {
+      "content": "<|/tool|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200025": {
+      "content": "<|tool_call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200026": {
+      "content": "<|/tool_call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200027": {
+      "content": "<|tool_response|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200028": {
+      "content": "<|tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200029": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|tool|>' + message['tools'] + '<|/tool|>' + '<|end|>' }}{% else %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

trainer_log.jsonl

@@ -0,0 +1,25 @@
+{"current_steps": 67, "total_steps": 1337, "loss": 4.4864, "lr": 4.925373134328357e-07, "epoch": 0.05009345794392523, "percentage": 5.01, "elapsed_time": "0:01:02", "remaining_time": "0:19:42"}
+{"current_steps": 134, "total_steps": 1337, "loss": 4.4815, "lr": 9.925373134328357e-07, "epoch": 0.10018691588785046, "percentage": 10.02, "elapsed_time": "0:02:06", "remaining_time": "0:18:56"}
+{"current_steps": 201, "total_steps": 1337, "loss": 4.3614, "lr": 9.451371571072319e-07, "epoch": 0.1502803738317757, "percentage": 15.03, "elapsed_time": "0:03:11", "remaining_time": "0:17:59"}
+{"current_steps": 250, "total_steps": 1337, "eval_loss": 4.165477752685547, "epoch": 0.18691588785046728, "percentage": 18.7, "elapsed_time": "0:04:16", "remaining_time": "0:18:34"}
+{"current_steps": 268, "total_steps": 1337, "loss": 4.1954, "lr": 8.894430590191188e-07, "epoch": 0.20037383177570092, "percentage": 20.04, "elapsed_time": "0:04:33", "remaining_time": "0:18:09"}
+{"current_steps": 335, "total_steps": 1337, "loss": 3.9922, "lr": 8.337489609310058e-07, "epoch": 0.2504672897196262, "percentage": 25.06, "elapsed_time": "0:05:37", "remaining_time": "0:16:48"}
+{"current_steps": 402, "total_steps": 1337, "loss": 3.6946, "lr": 7.780548628428927e-07, "epoch": 0.3005607476635514, "percentage": 30.07, "elapsed_time": "0:06:40", "remaining_time": "0:15:32"}
+{"current_steps": 469, "total_steps": 1337, "loss": 3.3914, "lr": 7.223607647547797e-07, "epoch": 0.3506542056074766, "percentage": 35.08, "elapsed_time": "0:07:45", "remaining_time": "0:14:20"}
+{"current_steps": 500, "total_steps": 1337, "eval_loss": 3.1697182655334473, "epoch": 0.37383177570093457, "percentage": 37.4, "elapsed_time": "0:08:32", "remaining_time": "0:14:18"}
+{"current_steps": 536, "total_steps": 1337, "loss": 3.154, "lr": 6.666666666666666e-07, "epoch": 0.40074766355140184, "percentage": 40.09, "elapsed_time": "0:09:06", "remaining_time": "0:13:37"}
+{"current_steps": 603, "total_steps": 1337, "loss": 2.9973, "lr": 6.109725685785536e-07, "epoch": 0.4508411214953271, "percentage": 45.1, "elapsed_time": "0:10:09", "remaining_time": "0:12:22"}
+{"current_steps": 670, "total_steps": 1337, "loss": 2.815, "lr": 5.552784704904405e-07, "epoch": 0.5009345794392523, "percentage": 50.11, "elapsed_time": "0:11:13", "remaining_time": "0:11:10"}
+{"current_steps": 737, "total_steps": 1337, "loss": 2.684, "lr": 4.995843724023275e-07, "epoch": 0.5510280373831775, "percentage": 55.12, "elapsed_time": "0:12:16", "remaining_time": "0:09:59"}
+{"current_steps": 750, "total_steps": 1337, "eval_loss": 2.6262145042419434, "epoch": 0.5607476635514018, "percentage": 56.1, "elapsed_time": "0:12:47", "remaining_time": "0:10:01"}
+{"current_steps": 804, "total_steps": 1337, "loss": 2.6152, "lr": 4.438902743142144e-07, "epoch": 0.6011214953271028, "percentage": 60.13, "elapsed_time": "0:13:39", "remaining_time": "0:09:03"}
+{"current_steps": 871, "total_steps": 1337, "loss": 2.5592, "lr": 3.881961762261014e-07, "epoch": 0.6512149532710281, "percentage": 65.15, "elapsed_time": "0:14:42", "remaining_time": "0:07:52"}
+{"current_steps": 938, "total_steps": 1337, "loss": 2.5099, "lr": 3.3250207813798835e-07, "epoch": 0.7013084112149532, "percentage": 70.16, "elapsed_time": "0:15:46", "remaining_time": "0:06:42"}
+{"current_steps": 1000, "total_steps": 1337, "eval_loss": 2.444204807281494, "epoch": 0.7476635514018691, "percentage": 74.79, "elapsed_time": "0:17:03", "remaining_time": "0:05:44"}
+{"current_steps": 1005, "total_steps": 1337, "loss": 2.4359, "lr": 2.7680798004987534e-07, "epoch": 0.7514018691588785, "percentage": 75.17, "elapsed_time": "0:17:08", "remaining_time": "0:05:39"}
+{"current_steps": 1072, "total_steps": 1337, "loss": 2.4193, "lr": 2.2111388196176226e-07, "epoch": 0.8014953271028037, "percentage": 80.18, "elapsed_time": "0:18:11", "remaining_time": "0:04:29"}
+{"current_steps": 1139, "total_steps": 1337, "loss": 2.4261, "lr": 1.6541978387364923e-07, "epoch": 0.851588785046729, "percentage": 85.19, "elapsed_time": "0:19:14", "remaining_time": "0:03:20"}
+{"current_steps": 1206, "total_steps": 1337, "loss": 2.3706, "lr": 1.0972568578553615e-07, "epoch": 0.9016822429906542, "percentage": 90.2, "elapsed_time": "0:20:17", "remaining_time": "0:02:12"}
+{"current_steps": 1250, "total_steps": 1337, "eval_loss": 2.3879618644714355, "epoch": 0.9345794392523364, "percentage": 93.49, "elapsed_time": "0:21:17", "remaining_time": "0:01:28"}
+{"current_steps": 1273, "total_steps": 1337, "loss": 2.3796, "lr": 5.403158769742311e-08, "epoch": 0.9517757009345794, "percentage": 95.21, "elapsed_time": "0:21:39", "remaining_time": "0:01:05"}
+{"current_steps": 1337, "total_steps": 1337, "epoch": 0.9996261682242991, "percentage": 100.0, "elapsed_time": "0:22:40", "remaining_time": "0:00:00"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c73af070a116712a13665b03156402a22c7b40bec0a1cf04cb8caeee48758be
+size 5688